Add to ORKGDeep neural networks are vulnerable to adversarial attacks. Most white-box attacks are based on the gradient of models to the input. Since the computation and memory budget, adversarial attacks based on the Hessian information are not paid enough attention. In this work, we study the attack performance and computation cost of the attack method based on the Hessian with a limited perturbation pixel number. Specifically, we propose the Limited Pixel BFGS (LP-BFGS) attack method by incorporating the BFGS algorithm. Some pixels are selected as perturbation pixels by the Integrated Gradient algorithm, which are regarded as optimization variables of the LP-BFGS attack. Experimental results across different networks and datasets with various pertu...
Recent advancements in the field of deep learning have substantially increased the adoption rate of ...
The aim of the project is to evaluate and improve adversarial attacks against deep learning models....
Deep learning networks have demonstrated high performance in a large variety of applications, such a...
After the discovery of adversarial examples and their adverse effects on deep learning models, many ...
Throughout the past five years, the susceptibility of neural networks to minimal adversarial perturb...
Deep neural networks are known to be vulnerable to adversarial examples crafted by adding human-impe...
Deep neural networks (DNNs) are susceptible to adversarial attacks, including the recently introduce...
Vulnerability to adversarial attacks is one of the principal hurdles to the adoption of deep learnin...
We propose new, more efficient targeted white-box attacks against deep neural networks. Our attacks ...
Depending on how much information an adversary can access to, adversarial attacks can be classified ...
In machine learning research, adversarial examples are normal inputs to a classifier that have been ...
Researches have shown that deep neural networks are vulnerable to malicious attacks, where adversari...
Solving for adversarial examples with projected gradient descent has been demonstrated to be highly ...
The vulnerability of deep neural network (DNN)-based systems makes them susceptible to adversarial p...
Adversarial patch is an important form of real-world adversarial attack that brings serious risks to...
Recent advancements in the field of deep learning have substantially increased the adoption rate of ...
The aim of the project is to evaluate and improve adversarial attacks against deep learning models....
Deep learning networks have demonstrated high performance in a large variety of applications, such a...
After the discovery of adversarial examples and their adverse effects on deep learning models, many ...
Throughout the past five years, the susceptibility of neural networks to minimal adversarial perturb...
Deep neural networks are known to be vulnerable to adversarial examples crafted by adding human-impe...
Deep neural networks (DNNs) are susceptible to adversarial attacks, including the recently introduce...
Vulnerability to adversarial attacks is one of the principal hurdles to the adoption of deep learnin...
We propose new, more efficient targeted white-box attacks against deep neural networks. Our attacks ...
Depending on how much information an adversary can access to, adversarial attacks can be classified ...
In machine learning research, adversarial examples are normal inputs to a classifier that have been ...
Researches have shown that deep neural networks are vulnerable to malicious attacks, where adversari...
Solving for adversarial examples with projected gradient descent has been demonstrated to be highly ...
The vulnerability of deep neural network (DNN)-based systems makes them susceptible to adversarial p...
Adversarial patch is an important form of real-world adversarial attack that brings serious risks to...
Recent advancements in the field of deep learning have substantially increased the adoption rate of ...
The aim of the project is to evaluate and improve adversarial attacks against deep learning models....
Deep learning networks have demonstrated high performance in a large variety of applications, such a...